Characterizing twitter discussions about HPV vaccines using topic modeling and community detection

Didi Surian, Dat Quoc Nguyen, Georgina Kennedy, Mark Johnson, Enrico Coiera, Adam G. Dunn

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Background: In public health surveillance, measuring how information enters and spreads through online communities may help us understand geographical variation in decision making associated with poor health outcomes. Objective: Our aim was to evaluate the use of community structure and topic modeling methods as a process for characterizing the clustering of opinions about human papillomavirus (HPV) vaccines on Twitter. Methods: The study examined Twitter posts (tweets) collected between October 2013 and October 2015 about HPV vaccines. We tested Latent Dirichlet Allocation and Dirichlet Multinomial Mixture (DMM) models for inferring topics associated with tweets, and community agglomeration (Louvain) and the encoding of random walks (Infomap) methods to detect community structure of the users from their social connections. We examined the alignment between community structure and topics using several common clustering alignment measures and introduced a statistical measure of alignment based on the concentration of specific topics within a small number of communities. Visualizations of the topics and the alignment between topics and communities are presented to support the interpretation of the results in context of public health communication and identification of communities at risk of rejecting the safety and efficacy of HPV vaccines. Results: We analyzed 285,417 Twitter posts (tweets) about HPV vaccines from 101,519 users connected by 4,387,524 social connections. Examining the alignment between the community structure and the topics of tweets, the results indicated that the Louvain community detection algorithm together with DMM produced consistently higher alignment values and that alignments were generally higher when the number of topics was lower. After applying the Louvain method and DMM with 30 topics and grouping semantically similar topics in a hierarchy, we characterized 163,148 (57.16%) tweets as evidence and advocacy, and 6244 (2.19%) tweets describing personal experiences. Among the 4548 users who posted experiential tweets, 3449 users (75.84%) were found in communities where the majority of tweets were about evidence and advocacy. Conclusions: The use of community detection in concert with topic modeling appears to be a useful way to characterize Twitter communities for the purpose of opinion surveillance in public health applications. Our approach may help identify online communities at risk of being influenced by negative opinions about public health interventions such as HPV vaccines.

LanguageEnglish
Article numbere232
Pages1-12
Number of pages12
JournalJournal of Medical Internet Research
Volume18
Issue number8
DOIs
Publication statusPublished - Aug 2016

Fingerprint

Papillomavirus Vaccines
Public Health Surveillance
Cluster Analysis
Public Health
Health Communication
Decision Making

Keywords

  • topic modelling
  • graph algorithms analysis
  • social media
  • public health surveillance

Cite this

@article{28d31f7d8a34470e9dbe4ef1956cb381,
title = "Characterizing twitter discussions about HPV vaccines using topic modeling and community detection",
abstract = "Background: In public health surveillance, measuring how information enters and spreads through online communities may help us understand geographical variation in decision making associated with poor health outcomes. Objective: Our aim was to evaluate the use of community structure and topic modeling methods as a process for characterizing the clustering of opinions about human papillomavirus (HPV) vaccines on Twitter. Methods: The study examined Twitter posts (tweets) collected between October 2013 and October 2015 about HPV vaccines. We tested Latent Dirichlet Allocation and Dirichlet Multinomial Mixture (DMM) models for inferring topics associated with tweets, and community agglomeration (Louvain) and the encoding of random walks (Infomap) methods to detect community structure of the users from their social connections. We examined the alignment between community structure and topics using several common clustering alignment measures and introduced a statistical measure of alignment based on the concentration of specific topics within a small number of communities. Visualizations of the topics and the alignment between topics and communities are presented to support the interpretation of the results in context of public health communication and identification of communities at risk of rejecting the safety and efficacy of HPV vaccines. Results: We analyzed 285,417 Twitter posts (tweets) about HPV vaccines from 101,519 users connected by 4,387,524 social connections. Examining the alignment between the community structure and the topics of tweets, the results indicated that the Louvain community detection algorithm together with DMM produced consistently higher alignment values and that alignments were generally higher when the number of topics was lower. After applying the Louvain method and DMM with 30 topics and grouping semantically similar topics in a hierarchy, we characterized 163,148 (57.16{\%}) tweets as evidence and advocacy, and 6244 (2.19{\%}) tweets describing personal experiences. Among the 4548 users who posted experiential tweets, 3449 users (75.84{\%}) were found in communities where the majority of tweets were about evidence and advocacy. Conclusions: The use of community detection in concert with topic modeling appears to be a useful way to characterize Twitter communities for the purpose of opinion surveillance in public health applications. Our approach may help identify online communities at risk of being influenced by negative opinions about public health interventions such as HPV vaccines.",
keywords = "topic modelling, graph algorithms analysis, social media, public health surveillance",
author = "Didi Surian and Nguyen, {Dat Quoc} and Georgina Kennedy and Mark Johnson and Enrico Coiera and Dunn, {Adam G.}",
year = "2016",
month = "8",
doi = "10.2196/jmir.6045",
language = "English",
volume = "18",
pages = "1--12",
journal = "Journal of Medical Internet Research",
issn = "1438-8871",
publisher = "JMIR PUBLICATIONS, INC",
number = "8",

}

Characterizing twitter discussions about HPV vaccines using topic modeling and community detection. / Surian, Didi; Nguyen, Dat Quoc; Kennedy, Georgina; Johnson, Mark; Coiera, Enrico; Dunn, Adam G.

In: Journal of Medical Internet Research, Vol. 18, No. 8, e232, 08.2016, p. 1-12.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Characterizing twitter discussions about HPV vaccines using topic modeling and community detection

AU - Surian, Didi

AU - Nguyen, Dat Quoc

AU - Kennedy, Georgina

AU - Johnson, Mark

AU - Coiera, Enrico

AU - Dunn, Adam G.

PY - 2016/8

Y1 - 2016/8

N2 - Background: In public health surveillance, measuring how information enters and spreads through online communities may help us understand geographical variation in decision making associated with poor health outcomes. Objective: Our aim was to evaluate the use of community structure and topic modeling methods as a process for characterizing the clustering of opinions about human papillomavirus (HPV) vaccines on Twitter. Methods: The study examined Twitter posts (tweets) collected between October 2013 and October 2015 about HPV vaccines. We tested Latent Dirichlet Allocation and Dirichlet Multinomial Mixture (DMM) models for inferring topics associated with tweets, and community agglomeration (Louvain) and the encoding of random walks (Infomap) methods to detect community structure of the users from their social connections. We examined the alignment between community structure and topics using several common clustering alignment measures and introduced a statistical measure of alignment based on the concentration of specific topics within a small number of communities. Visualizations of the topics and the alignment between topics and communities are presented to support the interpretation of the results in context of public health communication and identification of communities at risk of rejecting the safety and efficacy of HPV vaccines. Results: We analyzed 285,417 Twitter posts (tweets) about HPV vaccines from 101,519 users connected by 4,387,524 social connections. Examining the alignment between the community structure and the topics of tweets, the results indicated that the Louvain community detection algorithm together with DMM produced consistently higher alignment values and that alignments were generally higher when the number of topics was lower. After applying the Louvain method and DMM with 30 topics and grouping semantically similar topics in a hierarchy, we characterized 163,148 (57.16%) tweets as evidence and advocacy, and 6244 (2.19%) tweets describing personal experiences. Among the 4548 users who posted experiential tweets, 3449 users (75.84%) were found in communities where the majority of tweets were about evidence and advocacy. Conclusions: The use of community detection in concert with topic modeling appears to be a useful way to characterize Twitter communities for the purpose of opinion surveillance in public health applications. Our approach may help identify online communities at risk of being influenced by negative opinions about public health interventions such as HPV vaccines.

AB - Background: In public health surveillance, measuring how information enters and spreads through online communities may help us understand geographical variation in decision making associated with poor health outcomes. Objective: Our aim was to evaluate the use of community structure and topic modeling methods as a process for characterizing the clustering of opinions about human papillomavirus (HPV) vaccines on Twitter. Methods: The study examined Twitter posts (tweets) collected between October 2013 and October 2015 about HPV vaccines. We tested Latent Dirichlet Allocation and Dirichlet Multinomial Mixture (DMM) models for inferring topics associated with tweets, and community agglomeration (Louvain) and the encoding of random walks (Infomap) methods to detect community structure of the users from their social connections. We examined the alignment between community structure and topics using several common clustering alignment measures and introduced a statistical measure of alignment based on the concentration of specific topics within a small number of communities. Visualizations of the topics and the alignment between topics and communities are presented to support the interpretation of the results in context of public health communication and identification of communities at risk of rejecting the safety and efficacy of HPV vaccines. Results: We analyzed 285,417 Twitter posts (tweets) about HPV vaccines from 101,519 users connected by 4,387,524 social connections. Examining the alignment between the community structure and the topics of tweets, the results indicated that the Louvain community detection algorithm together with DMM produced consistently higher alignment values and that alignments were generally higher when the number of topics was lower. After applying the Louvain method and DMM with 30 topics and grouping semantically similar topics in a hierarchy, we characterized 163,148 (57.16%) tweets as evidence and advocacy, and 6244 (2.19%) tweets describing personal experiences. Among the 4548 users who posted experiential tweets, 3449 users (75.84%) were found in communities where the majority of tweets were about evidence and advocacy. Conclusions: The use of community detection in concert with topic modeling appears to be a useful way to characterize Twitter communities for the purpose of opinion surveillance in public health applications. Our approach may help identify online communities at risk of being influenced by negative opinions about public health interventions such as HPV vaccines.

KW - topic modelling

KW - graph algorithms analysis

KW - social media

KW - public health surveillance

UR - http://www.scopus.com/inward/record.url?scp=84989908186&partnerID=8YFLogxK

U2 - 10.2196/jmir.6045

DO - 10.2196/jmir.6045

M3 - Article

VL - 18

SP - 1

EP - 12

JO - Journal of Medical Internet Research

T2 - Journal of Medical Internet Research

JF - Journal of Medical Internet Research

SN - 1438-8871

IS - 8

M1 - e232

ER -